nano-banana-antigravity
Generate or edit images via Nano Banana Pro using Antigravity OAuth (no API key needed!)
Why use this skill?
Use the nano-banana-antigravity skill to generate and edit high-quality images via Gemini 3 Pro. No API keys required, WhatsApp HD optimized.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/cgnl/nano-banana-antigravityWhat This Skill Does
The nano-banana-antigravity skill provides a high-performance interface to Google's Gemini 3 Pro image generation models directly through your existing OpenClaw Antigravity OAuth credentials. By leveraging existing authenticated sessions, this tool eliminates the need for separate, cumbersome API keys. It allows users to generate high-fidelity visuals using simple command-line tools, while specifically catering to workflows that require WhatsApp-ready HD images. The skill includes advanced features such as automatic image format conversion, file size optimization for messaging platforms, and intelligent multi-image composition, all while maintaining seamless integration with your local file system.
Installation
To install this skill, use the ClawHub package manager. Run the following command in your terminal:
clawhub install openclaw/skills/skills/cgnl/nano-banana-antigravity
Before executing image generation tasks, ensure your environment is authenticated by running:
openclaw models auth login --provider google-antigravity
The tool will automatically detect credentials from your local configuration paths, including ~/.openclaw/credentials/ or standard OpenCode locations.
Use Cases
This skill is ideal for developers and power users who need to generate assets directly within their terminal-based workflows. Key use cases include:
- Rapid Prototyping: Generating assets for web development or UI/UX design.
- WhatsApp Communication: Creating optimized, high-resolution media that bypasses aggressive messaging app compression.
- Image Editing: Applying style modifications or adding elements to existing images using prompt-based instructions.
- Multi-Image Manipulation: Compositing several input images into a single cohesive scene for storytelling or data visualization.
Example Prompts
- "Generate a 4K 16:9 wallpaper of a cyberpunk city at night and save it as cyberpunk_hd.jpg using the WhatsApp tool."
- "Take the file user_photo.png and add a hat to the person in the image, saving the result as edited_hat.png."
- "Combine image1.png, image2.png, and image3.png into a single dramatic cinematic shot and save it as composite_scene.png."
Tips & Limitations
- WhatsApp Optimization: Always prefer
generate_whatsapp_hd.shfor messaging to ensure your images stay under the 6.28MB limit for best results. - Rate Limiting: This skill is robust; it automatically cycles through 12 different Antigravity accounts to avoid rate limits if one hits its quota.
- Performance: For best results, keep your prompts descriptive but concise. The tool will automatically timestamp files, so use descriptive names to keep your directory organized. If a Pro model is unreachable, the tool is designed to fail-over to standard models automatically.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-cgnl-nano-banana-antigravity": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-write, file-read, external-api
Related Skills
tado
Control your Tado smart thermostat - check temperature, set heating, manage home/away modes, and monitor presence via geolocation.
glm-coding-agent
Run Claude Code CLI with GLM 4.7 (via Z.AI) with automatic git safety net - checkpoint, experiment branch, review workflow. Cheap 200k context.
supermarkt-prijzen
Albert Heijn bonuses, product search, multi-store price comparison (12 supermarkets), recipe search by ingredients, and fridge scanner with vision AI.